import numpy as np 
import pandas as pd

%matplotlib inline
import matplotlib as mpl
import matplotlib.pyplot as plt
mpl.rc('axes', labelsize=14)
mpl.rc('xtick', labelsize=12)
mpl.rc('ytick', labelsize=12)

import seaborn as sns

data = pd.read_csv("ai4i2020.csv")

data.head()

	UDI	Product ID	Type	Air temperature [K]	Process temperature [K]	Rotational speed [rpm]	Torque [Nm]	Tool wear [min]	Machine failure	TWF	HDF	PWF	OSF	RNF
0	1	M14860	M	298.1	308.6	1551	42.8	0	0	0	0	0	0	0
1	2	L47181	L	298.2	308.7	1408	46.3	3	0	0	0	0	0	0
2	3	L47182	L	298.1	308.5	1498	49.4	5	0	0	0	0	0	0
3	4	L47183	L	298.2	308.6	1433	39.5	7	0	0	0	0	0	0
4	5	L47184	L	298.2	308.7	1408	40.0	9	0	0	0	0	0	0

data.shape

(10000, 14)

from ydata_profiling import ProfileReport

profile = ProfileReport(data, title="Pandas Profiling Report")

profile

Summarize dataset:   0%|          | 0/5 [00:00<?, ?it/s]

Generate report structure:   0%|          | 0/1 [00:00<?, ?it/s]

Render HTML:   0%|          | 0/1 [00:00<?, ?it/s]

data.describe().T

	count	mean	std	min	25%	50%	75%	max
UDI	10000.0	5000.50000	2886.895680	1.0	2500.75	5000.5	7500.25	10000.0
Air temperature [K]	10000.0	300.00493	2.000259	295.3	298.30	300.1	301.50	304.5
Process temperature [K]	10000.0	310.00556	1.483734	305.7	308.80	310.1	311.10	313.8
Rotational speed [rpm]	10000.0	1538.77610	179.284096	1168.0	1423.00	1503.0	1612.00	2886.0
Torque [Nm]	10000.0	39.98691	9.968934	3.8	33.20	40.1	46.80	76.6
Tool wear [min]	10000.0	107.95100	63.654147	0.0	53.00	108.0	162.00	253.0
Machine failure	10000.0	0.03390	0.180981	0.0	0.00	0.0	0.00	1.0
TWF	10000.0	0.00460	0.067671	0.0	0.00	0.0	0.00	1.0
HDF	10000.0	0.01150	0.106625	0.0	0.00	0.0	0.00	1.0
PWF	10000.0	0.00950	0.097009	0.0	0.00	0.0	0.00	1.0
OSF	10000.0	0.00980	0.098514	0.0	0.00	0.0	0.00	1.0
RNF	10000.0	0.00190	0.043550	0.0	0.00	0.0	0.00	1.0

data.select_dtypes(include=['object']).describe().T

	count	unique	top	freq
Product ID	10000	10000	M14860	1
Type	10000	3	L	6000

data.columns

Index(['UDI', 'Product ID', 'Type', 'Air temperature [K]',
       'Process temperature [K]', 'Rotational speed [rpm]', 'Torque [Nm]',
       'Tool wear [min]', 'Machine failure', 'TWF', 'HDF', 'PWF', 'OSF',
       'RNF'],
      dtype='object')

num_cols = ['Air temperature [K]', 'Process temperature [K]',
            'Rotational speed [rpm]', 'Torque [Nm]', 'Tool wear [min]']
cat_cols = ['Type', 'Failure type']
label = 'Machine failure'

data['Air temperature [K]'][data['Air temperature [K]'].isna().astype(int) == 1]

Series([], Name: Air temperature [K], dtype: float64)

plt.figure(figsize=(12, 12))
for i, col in enumerate(num_cols):
    plt.subplot(3, 2, i+1)
    sns.histplot(data, x=col, kde=True, alpha=0.2, color='red', bins=15)
    plt.title(col)
plt.suptitle("Data Distributions", fontsize=15)
plt.tight_layout()
plt.show()

c:\ProgramData\anaconda3\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
  with pd.option_context('mode.use_inf_as_na', True):
c:\ProgramData\anaconda3\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
  with pd.option_context('mode.use_inf_as_na', True):
c:\ProgramData\anaconda3\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
  with pd.option_context('mode.use_inf_as_na', True):
c:\ProgramData\anaconda3\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
  with pd.option_context('mode.use_inf_as_na', True):
c:\ProgramData\anaconda3\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
  with pd.option_context('mode.use_inf_as_na', True):

plt.figure(figsize=(10, 7))
for i, col in enumerate(num_cols):
    plt.subplot(2, 3, i+1)
    sns.rugplot(data, x=col, hue=label, height=0.1)
    sns.boxplot(data, x=col, width=0.25)
plt.suptitle("Data Distributions")
plt.tight_layout()
plt.show()

c:\ProgramData\anaconda3\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
  with pd.option_context('mode.use_inf_as_na', True):
c:\ProgramData\anaconda3\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
  with pd.option_context('mode.use_inf_as_na', True):
c:\ProgramData\anaconda3\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
  with pd.option_context('mode.use_inf_as_na', True):
c:\ProgramData\anaconda3\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
  with pd.option_context('mode.use_inf_as_na', True):
c:\ProgramData\anaconda3\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
  with pd.option_context('mode.use_inf_as_na', True):

plt.figure(figsize=(10, 7))
for i, col in enumerate(num_cols):
    plt.subplot(2, 3, i+1)
    sns.boxplot(data, x=label, y=col, width=0.5)
plt.suptitle("Data Distribution in Relation to Machine Failure")
plt.tight_layout()
plt.show()

#plt.figure(figsize = (6,6))
# , square = True, annot = True, cmap = 'Blues', linewidths = 0.5)
sns.heatmap(data[num_cols].corr(), annot=True, fmt=".2f")
plt.title("Heatmap Analysis")
plt.show()

data[num_cols].corr()

	Air temperature [K]	Process temperature [K]	Rotational speed [rpm]	Torque [Nm]	Tool wear [min]
Air temperature [K]	1.000000	0.876107	0.022670	-0.013778	0.013853
Process temperature [K]	0.876107	1.000000	0.019277	-0.014061	0.013488
Rotational speed [rpm]	0.022670	0.019277	1.000000	-0.875027	0.000223
Torque [Nm]	-0.013778	-0.014061	-0.875027	1.000000	-0.003093
Tool wear [min]	0.013853	0.013488	0.000223	-0.003093	1.000000

data.plot.hexbin(x='Air temperature [K]', y='Process temperature [K]',
                 gridsize=20, cmap='Purples', figsize=(5, 4))
plt.title("Hexbin Plot Between Process Temperature and Air Temperature")
plt.show()

data.plot.hexbin(x='Rotational speed [rpm]', y='Torque [Nm]',
                 gridsize=30, cmap='Purples', figsize=(5, 4))
plt.title("Hexbin Plot Between Torque and Rotational speed")
plt.show()

type_machine_failure = data[['Type', 'Machine failure']].pivot_table(index='Type', columns='Machine failure', aggfunc= lambda x: len(x), margins = True)
print(type_machine_failure)
plt.figure(figsize=(6,6))
sns.heatmap(type_machine_failure, annot=True, fmt='g', cmap='Blues', cbar=False, linewidths=0.5)
plt.title("Type vs Machine Failure")
plt.show()

Machine failure     0    1    All
Type                             
H                 982   21   1003
L                5765  235   6000
M                2914   83   2997
All              9661  339  10000

from pycaret.classification import *
s = setup(data, target = 'Machine failure', session_id = 42, data_split_stratify=True)

	Description	Value
0	Session id	42
1	Target	Machine failure
2	Target type	Binary
3	Original data shape	(10000, 14)
4	Transformed data shape	(10000, 16)
5	Transformed train set shape	(7000, 16)
6	Transformed test set shape	(3000, 16)
7	Numeric features	11
8	Categorical features	2
9	Preprocess	True
10	Imputation type	simple
11	Numeric imputation	mean
12	Categorical imputation	mode
13	Maximum one-hot encoding	25
14	Encoding method	None
15	Fold Generator	StratifiedKFold
16	Fold Number	10
17	CPU Jobs	-1
18	Use GPU	False
19	Log Experiment	False
20	Experiment Name	clf-default-name
21	USI	4ba6

best_model = compare_models(sort = 'AUC')

Initiated	. . . . . . . . . . . . . . . . . .	09:37:04
Status	. . . . . . . . . . . . . . . . . .	Loading Dependencies
Estimator	. . . . . . . . . . . . . . . . . .	Compiling Library

plt.figure(figsize = (4,3))
plot_model(best_model, plot = 'confusion_matrix')

plt.figure(figsize = (5,4))
plot_model(best_model, plot = 'auc')

plt.figure(figsize = (5, 4))
plot_model(best_model, plot = 'learning')

plot_model(best_model, plot = 'feature')

save_model(best_model, "ai4i2020_pycaret_model")

Transformation Pipeline and Model Successfully Saved

(Pipeline(memory=Memory(location=None),
          steps=[('numerical_imputer',
                  TransformerWrapper(exclude=None,
                                     include=['UDI', 'Air temperature [K]',
                                              'Process temperature [K]',
                                              'Rotational speed [rpm]',
                                              'Torque [Nm]', 'Tool wear [min]',
                                              'TWF', 'HDF', 'PWF', 'OSF',
                                              'RNF'],
                                     transformer=SimpleImputer(add_indicator=False,
                                                               copy=True,
                                                               fill_value=None,
                                                               keep_empty_features=False,
                                                               missing_valu...
                  TransformerWrapper(exclude=None, include=None,
                                     transformer=CleanColumnNames(match='[\\]\\[\\,\\{\\}\\"\\:]+'))),
                 ('trained_model',
                  LogisticRegression(C=1.0, class_weight=None, dual=False,
                                     fit_intercept=True, intercept_scaling=1,
                                     l1_ratio=None, max_iter=1000,
                                     multi_class='auto', n_jobs=None,
                                     penalty='l2', random_state=42,
                                     solver='lbfgs', tol=0.0001, verbose=0,
                                     warm_start=False))],
          verbose=False),
 'ai4i2020_pycaret_model.pkl')

plot_model(best_model, plot = 'calibration')

calibrated_model = calibrate_model(best_model)

Initiated	. . . . . . . . . . . . . . . . . .	09:38:35
Status	. . . . . . . . . . . . . . . . . .	Loading Dependencies
Estimator	. . . . . . . . . . . . . . . . . .	Compiling Library

	Accuracy	AUC	Recall	Prec.	F1	Kappa	MCC
Fold
0	0.9971	0.9670	0.9130	1.0000	0.9545	0.9531	0.9541
1	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000
2	0.9971	0.9558	0.9130	1.0000	0.9545	0.9531	0.9541
3	0.9986	1.0000	0.9583	1.0000	0.9787	0.9780	0.9782
4	0.9971	0.9581	0.9167	1.0000	0.9565	0.9550	0.9560
5	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000
6	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000
7	0.9986	1.0000	0.9583	1.0000	0.9787	0.9780	0.9782
8	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000
9	0.9986	0.9767	0.9583	1.0000	0.9787	0.9780	0.9782
Mean	0.9987	0.9858	0.9618	1.0000	0.9802	0.9795	0.9799
Std	0.0012	0.0182	0.0356	0.0000	0.0186	0.0192	0.0188

plot_model(calibrated_model, plot = 'calibration')

automl()

RidgeClassifier(alpha=1.0, class_weight=None, copy_X=True, fit_intercept=True,
                max_iter=None, positive=False, random_state=42, solver='auto',
                tol=0.0001)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

#create_app(best_model)